CVE-2024-43872

5.5 MEDIUM

📋 TL;DR

A race condition in the Linux kernel's RDMA hns driver can cause CPU cores to remain in interrupt context too long when handling CEQE events under heavy load, leading to system soft lockups. This affects systems using Huawei RDMA hardware with the vulnerable kernel driver. The vulnerability requires local access to trigger.

💻 Affected Systems

Products:
  • Linux kernel with hns RDMA driver
Versions: Kernel versions before fixes in stable trees (specific commits: 06580b33c183c9f98e2a2ca96a86137179032c08, 2fdf34038369c0a27811e7b4680662a14ada1d6b)
Operating Systems: Linux distributions using affected kernel versions
Default Config Vulnerable: ⚠️ Yes
Notes: Only affects systems with Huawei RDMA hardware using the hns driver. Requires RDMA functionality to be enabled and used.

📦 What is this software?

Linux Kernel by Linux

The Linux Kernel is the core component of the Linux operating system, serving as the critical interface between computer hardware and software processes. As the heart of millions of servers, cloud infrastructure, embedded systems, Android devices, and IoT deployments worldwide, the Linux Kernel mana...

Learn more about Linux Kernel →

⚠️ Risk & Real-World Impact

🔴

Worst Case

Complete system unresponsiveness (soft lockup) requiring hard reboot, causing denial of service for all services on affected system.

🟠

Likely Case

Temporary system slowdowns or hangs under specific RDMA workloads, potentially affecting application performance.

🟢

If Mitigated

Minor performance impact with proper kernel patches applied.

🌐 Internet-Facing: LOW - Requires local access to trigger via RDMA operations.
🏢 Internal Only: MEDIUM - Could be triggered by legitimate RDMA workloads or malicious local users.

🎯 Exploit Status

Public PoC: ✅ No
Weaponized: NO
Unauthenticated Exploit: ✅ No
Complexity: MEDIUM

Exploitation requires generating heavy CEQE load through RDMA operations, which typically requires local access and RDMA privileges.

🛠️ Fix & Mitigation

✅ Official Fix

Patch Version: Kernel versions containing commits 06580b33c183c9f98e2a2ca96a86137179032c08 and 2fdf34038369c0a27811e7b4680662a14ada1d6b

Vendor Advisory: https://git.kernel.org/stable/c/06580b33c183c9f98e2a2ca96a86137179032c08

Restart Required: Yes

Instructions:

1. Update Linux kernel to patched version from your distribution. 2. Reboot system to load new kernel. 3. Verify kernel version after reboot.

🔧 Temporary Workarounds

Limit RDMA workload

linux

Reduce or limit RDMA operations that generate CEQE events to prevent heavy load conditions.

# Monitor RDMA usage and implement rate limiting if possible
# Consider reducing RDMA-enabled application workloads

Disable RDMA if not needed

linux

Disable RDMA functionality if not required for system operations.

# Check if RDMA is enabled: lsmod | grep rdma
# Unload RDMA modules if possible: sudo modprobe -r rdma_ucm rdma_cm ib_umad ib_uverbs ib_core

🧯 If You Can't Patch

  • Implement strict access controls to prevent unauthorized local users from executing RDMA operations.
  • Monitor system for soft lockup events and implement automated alerting for investigation.

🔍 How to Verify

Check if Vulnerable:

Check kernel version and verify if RDMA hns driver is loaded: lsmod | grep hns && uname -r

Check Version:

uname -r

Verify Fix Applied:

Verify kernel version is updated and check dmesg for soft lockup messages after applying patch under RDMA load.

📡 Detection & Monitoring

Log Indicators:

  • Kernel soft lockup messages in dmesg or /var/log/kern.log
  • Watchdog timeout warnings
  • System hang reports

Network Indicators:

  • Unusual RDMA traffic patterns if monitored
  • Sudden drop in RDMA performance metrics

SIEM Query:

source="kernel" AND ("soft lockup" OR "watchdog" OR "BUG: soft lockup")

🔗 References

📤 Share & Export